Leanstral: Open-Source Foundation for Trustworthy Vibe-Coding★ 76
Mistral AI News6 days agoReleaseMistral AI introduced Leanstral, an open-source code agent designed for Lean 4 and formal proof engineering. The model is available through Apache 2.0 weights, Mistral Vibe, and a Labs API endpoint. Mistral positions it as a cost-efficient alternative for verified coding workflows, with FLTEval benchmarks comparing it against Claude family models and large open-source competitors.
LLM Research Papers: The 2026 List (January to May)
Ahead of AI (Raschka)8 days agoPaperSebastian Raschka compiles a curated reference list of LLM papers he bookmarked from January through May 2026. The list is not comprehensive, but organized around topics useful for future articles, lectures, code examples, and research work. Public sections emphasize reasoning, RL, efficient inference, long context, agent systems, tool use, coding agents, diffusion language models, and serving infrastructure.
Arithmetic Without Numbers: How LLMs Do Math
Hacker News (AI keywords)9 days agoCommentaryThe article asks whether LLM arithmetic is memorization, heuristics, real computation, or experimental assistance. It summarizes Rune experiments that decode operations and operands from frozen Llama activations, then route them to Python under a no-parser rule. The strongest supported claim is narrow: activation-derived tool arguments worked in scoped audits, while residual-state JIT replacement, long-number generation, and cross-model transfer remain brittle.
How LLMs Actually Work
Hacker News (AI keywords)10 days agoTutorialThe article explains how modern LLMs convert text into token IDs, embeddings, and position-aware vectors before passing them through stacked transformer blocks. It covers attention, multi-head attention, KV cache, GQA, feed-forward networks, MoE, residual streams, normalization, and decoding. Its goal is educational: helping readers understand the common architecture behind many current model families and read model cards or papers more confidently.
Transformer 中的混合專家模型 (MoE) 技術解析：原理、優缺點與實作挑戰★ 82
Hugging Face Blog108 days agoTutorialMixture of Experts (MoE) has become the mainstream architecture for current large language models (LLMs). This article takes an in-depth look at how MoE…
免費訓練 AI 模型！Hugging Face 聯手 Unsloth 推出 Hugging Face Jobs 免費微調服務★ 85
Hugging Face Blog114 days agoNew ToolHugging Face's official blog has announced exciting news for the open-source AI community: Hugging Face has formed a deep partnership with Unsloth — the…
Hugging Face 經典 NLP 課程正式轉型為 LLM 課程：迎向大語言模型時代的全面升級★ 85
Hugging Face Blog437 days agoTutorialHugging Face's "NLP Course" has long been a must-read classic for developers and researchers worldwide looking to enter the fields of Transformers and natural…
你也能設計出最先進的 Transformer 位置編碼：從直覺到 RoPE 的數學推導★ 75
Hugging Face Blog566 days agoTutorialThis educational article from Hugging Face aims to guide readers — in the most intuitive, step-by-step way — to "reinvent" RoPE (Rotary Position Embedding)…
混合專家模型 (Mixture of Experts, MoE) 技術詳解★ 85
Hugging Face Blog916 days agoTutorialMixture of Experts (MoE) has become a core technology for improving the performance and efficiency of today's large language models (LLMs). Traditional "dense…